Nemotron 3 Ultra

Name: Nemotron 3 Ultra
Brand: nvidia
SKU: nvidia/nvidia-nemotron-3-ultra-550b-a55b

nvidia·nvidia/nvidia-nemotron-3-ultra-550b-a55b·GA·Open weights·nemotron series

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Specs & pricing

Input / output per 1M tokens

Reference priceVenice AI

$0.63 / $3.13

Blended $1.25 · Cache read $0.19

Lowest paidOllama CloudCloud

$0.10 / $3.00

Blended $0.83 · 9× spread

Context

256,000

Output limit

32,768

Knowledge cutoff

—

Released / updated

2026-06-04 / 2026-06-23

Capabilities

✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments

⚠ Providers report capability flags inconsistently

Modalities

Text

Available at 7 providers7 with public prices

Priced only

Provider	Tier	Input	Output	Cache read	Cache write	Context	Output limit
Ollama Cloud nemotron-3-ultra	Cloud	$0.10	$3.00	$0.10	—	262,144 ⚠	128,000
CoreWeave nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	Cloud	$0.50	$2.15	$0.10	—	262,144 ⚠	262,144
Requesty nvidia-nemotron-3-ultra	Gateway	$0.50	$2.50	—	—	262,144 ⚠	131,072
Vercel AI Gateway nvidia/nemotron-3-ultra-550b-a55b	Cloud	$0.60	$2.40	$0.12	—	1,000,000 ⚠	65,000
Baseten nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	Cloud	$0.60	$2.40	$0.12	—	202,800 ⚠	202,800
DigitalOcean nemotron-3-ultra-550b	Cloud	$0.90	$1.70	$0.18	—	131,072 ⚠	131,072
Venice AI	Gateway	$0.63	$3.13	$0.19	—	256,000	32,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = noneeffort = loweffort = mediumeffort = higheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 7 providers.

Your usage cost

Input tokens / month

Output tokens / month

Cache hit rate

Common scenarios

1CoreWeave$159.50

2Ollama Cloud$170.00

3DigitalOcean$178.60

4Vercel AI Gateway$182.40

5Baseten$182.40

6Requesty$225.00

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended

Available at 7 providers7 with public prices

Priced only

Provider	Tier	Input	Output	Cache read	Cache write	Context	Output limit
Ollama Cloud nemotron-3-ultra	Cloud	$0.10	$3.00	$0.10	—	262,144 ⚠	128,000
CoreWeave nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	Cloud	$0.50	$2.15	$0.10	—	262,144 ⚠	262,144
Requesty nvidia-nemotron-3-ultra	Gateway	$0.50	$2.50	—	—	262,144 ⚠	131,072
Vercel AI Gateway nvidia/nemotron-3-ultra-550b-a55b	Cloud	$0.60	$2.40	$0.12	—	1,000,000 ⚠	65,000
Baseten nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	Cloud	$0.60	$2.40	$0.12	—	202,800 ⚠	202,800
DigitalOcean nemotron-3-ultra-550b	Cloud	$0.90	$1.70	$0.18	—	131,072 ⚠	131,072
Venice AI	Gateway	$0.63	$3.13	$0.19	—	256,000	32,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Price historyone sample accumulated per data sync

Input listOutput listMin blended

Nemotron 3 Ultra

Specs & pricing

Available at 7 providers7 with public prices

Reasoning control

Your usage cost

Price historyone sample accumulated per data sync

Related models

Nemotron 3 Ultra

Specs & pricing

Available at 7 providers7 with public prices

Reasoning control

Your usage cost

Price historyone sample accumulated per data sync

Related models